© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3547
    Prev
    Next
    INDEX
    Explanations

    mentions of spokespersons or representatives in a context related to communication or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isay
    -0.09
    пиÑģ
    -0.07
    ÙĦات
    -0.07
    еко
    -0.07
    stroy
    -0.07
    azaar
    -0.07
    spiel
    -0.07
    space
    -0.07
    affe
    -0.07
    ousse
    -0.06
    POSITIVE LOGITS
     for
    0.10
     spokes
    0.07
    Ðĭ
    0.06
     длÑı
    0.06
    _for
    0.06
    HIP
    0.06
    ForResult
    0.06
    684
    0.06
    889
    0.06
     cum
    0.06
    Activations Density 0.005%

    No Known Activations